# aingdesk/AingDesk

AingDesk是一款简单好用的AI助手，支持知识库、模型API、分享、联网搜索、智能体，它还在飞快成长中。 AingDesk is a simple and easy-to-use AI assistant that supports knowledge bases, model APIs, sharing, internet search, and intelligent agents. It is still growing rapidly.

Repository: https://github.com/aingdesk/AingDesk
Canonical: https://ross.abutalabs.com/products/aingdesk
Homepage: https://www.aingdesk.com
Language: TypeScript
License: MIT
License Family: permissive
Topics: deepseek, electron, llm, localai, nodejs, ollama
Last push: 2026-06-04T15:20:40+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 85, release rhythm 40, longevity 40
- inputs: {"age_days": 567, "days_push": 90, "days_rel": 463, "gap_med": 1, "n_releases_24m": 20}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2533, forks 287 (observed 2026-08-28T04:06:59.035781+00:00)

## What it is
AingDesk is an open-source, MIT-licensed AI assistant application for running local AI models (e.g., via Ollama) and third-party model APIs with a friendly desktop or server-hosted interface. It supports local knowledge bases, intelligent agents, MCP client integration, web search, and sharing assistants with others.

## Use cases
- run local AI models on my desktop without technical setup
- build a chatbot grounded in my own documents
- create a knowledge base from my PDFs and files
- deploy a self-hosted AI assistant on a server with Docker
- share an AI assistant with my team or friends
- connect AI agents to tools via MCP
- chat with DeepSeek or other model APIs in one app
- give an AI assistant web search access

## When to choose
- you want a beginner-friendly GUI for local models like Ollama or DeepSeek
- you need knowledge-base (RAG) chat without writing code
- you want a self-hosted assistant deployable via Docker with sharing support
- you need MCP client support and agent creation in a desktop app

## When to avoid
- you need a headless library or SDK to embed LLM features into your own code
- you need highly scalable multi-tenant enterprise RAG infrastructure
- you only want a minimal CLI for local model inference
- you require mature multi-model simultaneous conversations (still upcoming)

## Facets
- artifact type: application
- maturity: active
- function: chatbot, rag, llm-inference, agent-framework, mcp, web-scraping, self-hosted
- domain: artificial-intelligence, large-language-models, chatbots, self-hosted, cross-platform
- platform: windows, self-hosted, cross-platform
- tags: local-ai, knowledge-base, ollama, deepseek, model-api, ai-assistant, web-search, intelligent-agents, shareable, retrieval-augmented-generation, ai-agents, macos, docker, electron, nodejs

## Member repositories
- aingdesk/AingDesk (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:59.035781+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:25:15.847957+00:00, confidence not recorded.
  - readme: https://github.com/aingdesk/AingDesk (fetched 2026-08-28T04:06:59.035781+00:00, sha 47a22ff85ff7)
  - homepage: https://www.aingdesk.com (fetched 2026-08-29T10:07:47.438315+00:00, sha 970f9d2db1d4)
  - site_page: https://www.aingdesk.com/docs (fetched 2026-08-29T10:07:47.441934+00:00, sha 75cdaee31da6)
  - site_page: https://www.aingdesk.com/docs/api (fetched 2026-08-29T10:07:47.444067+00:00, sha d332bddc9e74)
  - site_page: https://www.aingdesk.com/docs/enterprise (fetched 2026-08-29T10:07:47.445922+00:00, sha fe9d22a82e42)
- Data as of 2026-08-30T08:39:29.467469+00:00.